espnet3.systems.base.inference.infer

source

espnet3.systems.base.inference.infer(config: DictConfig)

Run inference over all configured test sets and write SCP files.

This entrypoint expects each inference result to be a dict containing a sample identifier under utt_id (or the configured idx_key), plus one value per output field. The final SCP files are always written under:

${inference_dir}/<test_name>/<field>.scp

where each line is:

<utt_id> <value_or_path>

Primitive values are written directly into SCP files.

Example return value from output_fn or directly from the inference model:

{"utt_id": "utt1", "hyp": "hello world"}

Generated SCP:

inference_dir/test-clean/hyp.scp
  utt1 hello world

Non-scalar values are serialized through espnet3.utils.writer_utils.write_artifact(). That function documents the detailed rules for JSON, NPY, pickle, WAV, and custom writer cases.

Example WAV configuration:

output_artifacts:
  audio:
    type: wav
    sample_rate: 16000

Example return value from output_fn:

{"utt_id": "utt1", "audio": waveform_numpy}

Top-level list / tuple outputs are not supported. Each output field must be a single value. If you need structured content, return a dict and let it be serialized as JSON.

• Parameters:config – Hydra/OmegaConf configuration containing the dataset, inference directory, provider/runner definitions, and optional output_artifacts writer settings.